{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,12,7]],"date-time":"2024-12-07T05:22:51Z","timestamp":1733548971972,"version":"3.30.1"},"reference-count":14,"publisher":"Institute of Electronics, Information and Communications Engineers (IEICE)","issue":"12","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Trans. Inf. & Syst."],"published-print":{"date-parts":[[2024,12,1]]},"DOI":"10.1587\/transinf.2024edl8014","type":"journal-article","created":{"date-parts":[[2024,8,25]],"date-time":"2024-08-25T22:11:53Z","timestamp":1724623913000},"page":"1546-1549","source":"Crossref","is-referenced-by-count":0,"title":["CNN-Based Feature Integration Network for Speech Enhancement in Microphone Arrays"],"prefix":"10.1587","volume":"E107.D","author":[{"given":"Ji","family":"XI","sequence":"first","affiliation":[{"name":"School of Computer Information Engineering, Changzhou Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pengxu","family":"JIANG","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, Southeast University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yue","family":"XIE","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, Nanjing Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"JIANG","sequence":"additional","affiliation":[{"name":"School of Computer Information Engineering, Changzhou Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"DING","sequence":"additional","affiliation":[{"name":"School of Computer Information Engineering, Changzhou Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"532","reference":[{"key":"1","doi-asserted-by":"publisher","unstructured":"[1] N. Das, S. Chakraborty, J. Chaki, N. Padhy, and N. Dey, \u201cFundamentals, present and future perspectives of speech enhancement,\u201d International Journal of Speech Technology, vol.24, no.4, pp.883-901, 2021. 10.1007\/s10772-020-09674-2","DOI":"10.1007\/s10772-020-09674-2"},{"key":"2","doi-asserted-by":"publisher","unstructured":"[2] S. Vihari, A.S. Murthy, P. Soni, and D.C. Naik, \u201cComparison of speech enhancement algorithms,\u201d Procedia computer science, vol.89, pp.666-676, 2016. 10.1016\/j.procs.2016.06.032","DOI":"10.1016\/j.procs.2016.06.032"},{"key":"3","doi-asserted-by":"publisher","unstructured":"[3] X. Cui, Z. Chen, and F. Yin, \u201cMulti-objective based multi-channel speech enhancement with BiLSTM network,\u201d Applied Acoustics, vol.177, p.107927, 2021. 10.1016\/j.apacoust.2021.107927","DOI":"10.1016\/j.apacoust.2021.107927"},{"key":"4","doi-asserted-by":"publisher","unstructured":"[4] H. Taherian, Z.-Q. Wang, J. Chang, and D.L. Wang, \u201cRobust speaker recognition based on single-channel and multi-channel speech enhancement,\u201d IEEE\/ACM Trans. Audio, Speech, Language Process., vol.28, pp.1293-1302, 2020. 10.1109\/taslp.2020.2986896","DOI":"10.1109\/TASLP.2020.2986896"},{"key":"5","doi-asserted-by":"publisher","unstructured":"[5] K. Tan, X. Zhang, and D.L. Wang, \u201cDeep learning based real-time speech enhancement for dual-microphone mobile phones,\u201d IEEE\/ACM Trans. Audio, Speech, Language Process., vol.29, pp.1853-1863, 2021. 10.1109\/taslp.2021.3082318","DOI":"10.1109\/TASLP.2021.3082318"},{"key":"6","doi-asserted-by":"publisher","unstructured":"[6] M. Barhoush, A. Hallawa, A. Peine, L. Martin, and A. Schmeink, \u201cLocalization-Driven Speech Enhancement in Noisy Multi-Speaker Hospital Environments Using Deep Learning and Meta Learning,\u201d IEEE\/ACM Trans. Audio, Speech, Language Process., vol.31, pp.670-683, 2022. 10.1109\/taslp.2022.3231700","DOI":"10.1109\/TASLP.2022.3231700"},{"key":"7","doi-asserted-by":"crossref","unstructured":"[7] A. Pandey and D. Wang, \u201cDensely Connected Neural Network with Dilated Convolutions for Real-Time Speech Enhancement in The Time Domain,\u201d ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Barcelona, Spain, pp.6629-6633, 2020. 10.1109\/icassp40776.2020.9054536","DOI":"10.1109\/ICASSP40776.2020.9054536"},{"key":"8","doi-asserted-by":"crossref","unstructured":"[8] K. Tan and D. Wang, \u201cA convolutional recurrent neural network for real-time speech enhancement,\u201d Proc. Interspeech, pp.3229-3233, Sept. 2018. 10.21437\/interspeech.2018-1405","DOI":"10.21437\/Interspeech.2018-1405"},{"key":"9","doi-asserted-by":"crossref","unstructured":"[9] S.R. Park and J.W. Lee, \u201cA fully convolutional neural network for speech enhancement,\u201d arXiv preprint arXiv:1609.07132, 2016.","DOI":"10.21437\/Interspeech.2017-1465"},{"key":"10","doi-asserted-by":"publisher","unstructured":"[10] A. Pandey and D.L. Wang, \u201cDense CNN with self-attention for time-domain speech enhancement,\u201d IEEE\/ACM Trans. Audio, Speech, Language Process., vol.29, pp.1270-1279, 2021. 10.1109\/taslp.2021.3064421","DOI":"10.1109\/TASLP.2021.3064421"},{"key":"11","doi-asserted-by":"crossref","unstructured":"[11] J. Barker, R. Marxer, E. Vincent, and S. Watanabe, \u201cThe third \u2018CHiME\u2019 speech separation and recognition challenge: Dataset, task and baselines,\u201d 2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), IEEE, pp.504-511, 2015. 10.1109\/asru.2015.7404837","DOI":"10.1109\/ASRU.2015.7404837"},{"key":"12","doi-asserted-by":"publisher","unstructured":"[12] E.A. Lehmann and A.M. Johansson, \u201cDiffuse reverberation model for efficient image-source simulation of room impulse responses,\u201d IEEE Trans. Audio, Speech, Language Process., vol.18, no.6, pp.1429-1439, 2010. 10.1109\/tasl.2009.2035038","DOI":"10.1109\/TASL.2009.2035038"},{"key":"13","doi-asserted-by":"crossref","unstructured":"[13] C.H. Taal, R.C. Hendriks, R. Heusdens, and J. Jensen, \u201cA short-time objective intelligibility measure for time-frequency weighted noisy speech,\u201d 2010 IEEE international conference on acoustics, speech and signal processing, IEEE, pp.4214-4217, 2010. 10.1109\/icassp.2010.5495701","DOI":"10.1109\/ICASSP.2010.5495701"},{"key":"14","doi-asserted-by":"publisher","unstructured":"[14] M. Torcoli, T. Kastner, and J. Herre, \u201cObjective measures of perceptual audio quality reviewed: An evaluation of their application domain dependence,\u201d IEEE\/ACM Trans. Audio, Speech, Language Process., vol.29, pp.1530-1541, 2021. 10.1109\/taslp.2021.3069302","DOI":"10.1109\/TASLP.2021.3069302"}],"container-title":["IEICE Transactions on Information and Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E107.D\/12\/E107.D_2024EDL8014\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,7]],"date-time":"2024-12-07T03:24:43Z","timestamp":1733541883000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E107.D\/12\/E107.D_2024EDL8014\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,1]]},"references-count":14,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2024]]}},"URL":"https:\/\/doi.org\/10.1587\/transinf.2024edl8014","relation":{},"ISSN":["0916-8532","1745-1361"],"issn-type":[{"type":"print","value":"0916-8532"},{"type":"electronic","value":"1745-1361"}],"subject":[],"published":{"date-parts":[[2024,12,1]]},"article-number":"2024EDL8014"}}